{"id":"https://openalex.org/W2938792232","doi":"https://doi.org/10.1109/icassp.2019.8682824","title":"Comparison of Data Augmentation and Adaptation Strategies for Code-switched Automatic Speech Recognition","display_name":"Comparison of Data Augmentation and Adaptation Strategies for Code-switched Automatic Speech Recognition","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2938792232","doi":"https://doi.org/10.1109/icassp.2019.8682824","mag":"2938792232"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8682824","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682824","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101706633","display_name":"Min Ma","orcid":"https://orcid.org/0000-0002-3132-4898"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Min Ma","raw_affiliation_strings":["Google Inc., USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc., USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071715737","display_name":"Bhuvana Ramabhadran","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bhuvana Ramabhadran","raw_affiliation_strings":["Google Inc., USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc., USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027399854","display_name":"Jesse Emond","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jesse Emond","raw_affiliation_strings":["Google Inc., USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc., USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102902866","display_name":"Andrew Rosenberg","orcid":"https://orcid.org/0000-0003-1780-4390"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew Rosenberg","raw_affiliation_strings":["Google Inc., USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc., USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055592425","display_name":"Fadi Biadsy","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fadi Biadsy","raw_affiliation_strings":["Google Inc., USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc., USA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6081","last_page":"6085"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9934999942779541,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8524712324142456},{"id":"https://openalex.org/keywords/bengali","display_name":"Bengali","score":0.8085430264472961},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.600324273109436},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5844219326972961},{"id":"https://openalex.org/keywords/perplexity","display_name":"Perplexity","score":0.5763999223709106},{"id":"https://openalex.org/keywords/dictation","display_name":"Dictation","score":0.5510650873184204},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5472946763038635},{"id":"https://openalex.org/keywords/code-switching","display_name":"Code-switching","score":0.5388448238372803},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.52281653881073},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4552418887615204},{"id":"https://openalex.org/keywords/principle-of-maximum-entropy","display_name":"Principle of maximum entropy","score":0.4352218210697174},{"id":"https://openalex.org/keywords/transliteration","display_name":"Transliteration","score":0.42808327078819275},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.12370657920837402},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09093397855758667}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8524712324142456},{"id":"https://openalex.org/C19235068","wikidata":"https://www.wikidata.org/wiki/Q9610","display_name":"Bengali","level":2,"score":0.8085430264472961},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.600324273109436},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5844219326972961},{"id":"https://openalex.org/C100279451","wikidata":"https://www.wikidata.org/wiki/Q372193","display_name":"Perplexity","level":3,"score":0.5763999223709106},{"id":"https://openalex.org/C2779077324","wikidata":"https://www.wikidata.org/wiki/Q1087138","display_name":"Dictation","level":2,"score":0.5510650873184204},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5472946763038635},{"id":"https://openalex.org/C18552078","wikidata":"https://www.wikidata.org/wiki/Q255615","display_name":"Code-switching","level":2,"score":0.5388448238372803},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.52281653881073},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4552418887615204},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.4352218210697174},{"id":"https://openalex.org/C520968082","wikidata":"https://www.wikidata.org/wiki/Q134550","display_name":"Transliteration","level":2,"score":0.42808327078819275},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.12370657920837402},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09093397855758667},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2019.8682824","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682824","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7300000190734863}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W87424008","https://openalex.org/W761725120","https://openalex.org/W1999965501","https://openalex.org/W2039387825","https://openalex.org/W2046932483","https://openalex.org/W2055543848","https://openalex.org/W2059588204","https://openalex.org/W2061272101","https://openalex.org/W2072566913","https://openalex.org/W2098355803","https://openalex.org/W2114016253","https://openalex.org/W2118692229","https://openalex.org/W2121227244","https://openalex.org/W2127141656","https://openalex.org/W2134817403","https://openalex.org/W2139604620","https://openalex.org/W2146502635","https://openalex.org/W2153433699","https://openalex.org/W2293634267","https://openalex.org/W2296014541","https://openalex.org/W2625701807","https://openalex.org/W2747467128","https://openalex.org/W2798348125","https://openalex.org/W2883449998","https://openalex.org/W2883989418","https://openalex.org/W2913739034","https://openalex.org/W2914699162","https://openalex.org/W2950173449","https://openalex.org/W2963945964","https://openalex.org/W4298316246","https://openalex.org/W6603544574","https://openalex.org/W6622259991","https://openalex.org/W6677631519","https://openalex.org/W6678277124","https://openalex.org/W6680125536","https://openalex.org/W6680986496","https://openalex.org/W6681435938","https://openalex.org/W6696934422","https://openalex.org/W6697421373","https://openalex.org/W6703490699","https://openalex.org/W6728813052","https://openalex.org/W6759290872"],"related_works":["https://openalex.org/W2130100766","https://openalex.org/W4288023470","https://openalex.org/W2985347586","https://openalex.org/W3082735059","https://openalex.org/W2507865718","https://openalex.org/W2884096449","https://openalex.org/W2251131759","https://openalex.org/W2977094753","https://openalex.org/W2969143370","https://openalex.org/W2938792232"],"abstract_inverted_index":{"Code-switching":[0,23],"occurs":[1],"when":[2],"the":[3,33,70,125,131],"speaker":[4],"alternates":[5],"between":[6],"two":[7,84],"or":[8,11],"more":[9,139],"languages":[10],"dialects.":[12],"It":[13],"is":[14,41,136],"a":[15,25,42],"pervasive":[16],"phenomenon":[17],"in":[18,27],"most":[19],"Indic":[20],"spoken":[21],"languages.":[22],"poses":[24],"challenge":[26],"language":[28,58,108],"modeling":[29],"as":[30,64],"it":[31],"complicates":[32],"orthographic":[34],"realization":[35],"of":[36,44],"text,":[37],"and":[38,54,62,77,91,103,120],"generally,":[39],"there":[40],"shortage":[43],"code-switched":[45,71],"data.":[46,141],"In":[47],"this":[48],"paper,":[49],"we":[50,67],"investigate":[51],"data":[52],"augmentation":[53],"adaptation":[55,115],"strategies":[56,116],"for":[57,117],"modeling.":[59],"Using":[60],"Bengali":[61,76],"English":[63,78],"an":[65],"example,":[66],"study":[68],"augmenting":[69],"transcripts":[72],"with":[73,99],"separate":[74],"transliterated":[75],"corpora.":[79],"We":[80,93,111],"present":[81],"results":[82],"on":[83,96,138],"speech":[85],"recognition":[86],"tasks,":[87],"namely,":[88],"voice":[89],"search":[90],"dictation.":[92],"show":[94],"improvements":[95],"both":[97],"tasks":[98],"Maximum":[100],"Entropy":[101],"(MaxEnt)":[102],"Long":[104],"Short-Term":[105],"Memory":[106],"(LSTM)":[107],"models":[109],"(LMs).":[110],"also":[112],"explore":[113],"different":[114],"MaxEnt":[118,133],"LM":[119,129,134],"LSTM":[121,128],"LM,":[122],"demonstrating":[123],"that":[124],"transliteration-based":[126],"data-augmented":[127],"matches":[130],"adapted":[132],"which":[135],"trained":[137],"Bengali-English":[140]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}